Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Face recognition using kernel direct discriminant analysis algorithms.

Juwei Lu1, K N Plataniotis, A N Venetsanopoulos

  • 1Dept. of Electr. and Comput. Eng., Toronto Univ., Ont., Canada.

IEEE Transactions on Neural Networks
|February 2, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Face Feature Weighted Fusion Based on Fuzzy Membership Degree for Video Face Recognition.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same author

Group-membership reinforcement for straight edges based on Bayesian networks.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Angular map-driven snakes with application to object shape description in color images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Face recognition with radial basis function (RBF) neural networks.

IEEE transactions on neural networks·2008
Same author

Face recognition using LDA-based algorithms.

IEEE transactions on neural networks·2008
Same author

Ensemble-based discriminant learning with boosting for face recognition.

IEEE transactions on neural networks·2006
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a new kernel method for face recognition (FR) that effectively handles complex variations and the small sample size problem. The proposed approach significantly improves accuracy compared to existing kernel-based face recognition techniques.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Face recognition (FR) systems require low-dimensional feature representations with high discriminatory power.
  • Linear techniques like PCA and LDA struggle with the nonlinear complexity of face image distributions due to variations in viewpoint, illumination, and expression.
  • The small sample size (SSS) problem is prevalent in FR tasks, hindering the performance of traditional methods.

Purpose of the Study:

  • To propose a novel kernel machine-based discriminant analysis method for face recognition.
  • To address the inherent nonlinearity in face image data.
  • To effectively solve the small sample size problem in face recognition.

Main Methods:

  • Developed a kernel machine-based discriminant analysis algorithm.

Related Experiment Videos

  • Utilized kernel methods to handle nonlinear distributions of face patterns.
  • Evaluated the method on the multiview UMIST face database for classification error rate.

    • Main Results:

    • The proposed method achieves excellent performance using a minimal set of features.
    • Demonstrated significant reduction in error rates compared to established kernel approaches.
    • Achieved error rates approximately 34% and 48% lower than kernel-PCA (KPCA) and generalized discriminant analysis (GDA), respectively.

    Conclusions:

    • The proposed kernel-based discriminant analysis is a robust and effective solution for face recognition.
    • The method excels in handling nonlinear face variations and the small sample size challenge.
    • Offers superior performance over existing kernel FR techniques, paving the way for more reliable systems.